INDEX

Explanations

words and phrases related to educational courses and their frameworks

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Hlav

-0.15

ÏħÎ³

-0.15

ombine

-0.15

ertino

-0.14

wei

-0.14

ãĤĤãģªãģĦ

-0.14

NotSupportedException

-0.14

spe

-0.14

wk

-0.14

 Fade

-0.14

POSITIVE LOGITS

 popular

0.17

ibilities

0.14

.gdx

0.14

popular

0.13

oso

0.13

 thousands

0.13

RIES

0.13

rani

0.13

_goto

0.13

 tens

0.13

Activations Density 0.005%

words and phrases related to educational courses and their frameworks

No Comments

No Known Activations